AI Paper Atlas

Research map / Video / Video segmentation and tracking

Motion Sensitive Contrastive Learning for Self-Supervised Video Representation

Jingcheng Ni, Nan Zhou, Jie Qin, Qian Wu, Junqi Liu, Boxun Li, Di Huang

ECCV 2022 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 14 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add L_RF cross-modality loss (ablation)MSCL · UCF101 finetunetop-1 accuracy: 65.1 -> 71.4Improved
add L_LMC local motion loss (ablation)MSCL · UCF101 finetunetop-1 accuracy: 65.1 -> 70.5Improved
add L_LMC on top of L_RF (ablation)MSCL · UCF101 finetunetop-1 accuracy: 71.4 -> 75.6Improved
add L_LMC on top of L_RF (ablation)MSCL · UCF101 retrieval R@1R@1: 36.5 -> 45.7Improved
add flow rotation augmentation (FA) (ablation)MSCL · UCF101 finetunetop-1 accuracy: 75.6 -> 76.8Improved
add motion differential sampling (MDS) (ablation)MSCL · UCF101 finetunetop-1 accuracy: 75.6 -> 76.4Improved
combine FA and MDS (ablation)MSCL · UCF101 finetunetop-1 accuracy: 75.6 -> 77.3Improved
use 3D backbone in flow pathway when only L_RF is used (ablation)MSCL · UCF101 finetunetop-1 accuracy: 71.4 -> 71.2No clear effect
use 2D ResNet-18 instead of R3D-18 for the flow pathway (ablation)MSCL · UCF101 finetunetop-1 accuracy: 71.3 -> 72.3Improved
add reflect padding for 3D flow backbone instead of zero padding (ablation)MSCL · UCF101 finetunetop-1 accuracy: 71.3 -> 70.7Hurt
add TPN in RGB pathway (ablation)MSCL · UCF101 finetunetop-1 accuracy: 72.3 -> 75.6Improved
use flow input instead of motion boundary for L_LMC (ablation)MSCL · UCF101 finetunetop-1 accuracy: 68.2 -> 70.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy